© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166547
    Prev
    Next
    INDEX
    Explanations

    purpose fulfilled or completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᄐ
    0.38
     continually
    0.36
    ম্ব
    0.35
     backtrack
    0.35
     tabindex
    0.34
     continuously
    0.34
    樾
    0.34
    泼
    0.34
    spr
    0.33
    selectTable
    0.33
    POSITIVE LOGITS
     satisfied
    0.69
     fulfilled
    0.64
     accomplishing
    0.64
     achieved
    0.60
     accomplished
    0.60
     achieving
    0.60
     Ful
    0.59
     fulfillment
    0.58
     fulfilling
    0.55
     satisf
    0.55
    Activations Density 0.039%

    No Known Activations